Persona-Conditioned Adversarial Prompting: Multi-Identity Red-Teaming for Adversarial Discovery and Mitigation

Abstract

Automated red-teaming for LLMs often discovers narrow attack slices, missing diverse real-world threats, and yielding insufficient data for safety fine-tuning. We introduce Persona-Conditioned Adversarial Prompting (PCAP), which conditions adversarial search on diverse attacker personas (e.g., doctors, students, malicious actors) and strategy sets to explore realistic attack scenarios. By running parallel persona-conditioned searches, PCAP discovers transferable jailbreaks across different conte

Categories

Framework mappings

Suggested from the entry's categories.

@misc{morasso2026personaconditionedb,
  title = {{Persona-Conditioned Adversarial Prompting: Multi-Identity Red-Teaming for Adversarial Discovery and Mitigation}},
  author = {Cristian Morasso and Anisa Halimi and Muhammad Zaid Hameed and Douglas Leith},
  year = {2026},
  month = may,
  eprint = {2605.11730},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.11730}
}